Update app.py

app.py

@@ -17,7 +17,7 @@ def round_time_resolution(time_resolution):
 
 def predict(audio_path, time_resolution):
     audio_tagging_time_resolution = round_time_resolution(time_resolution)
-    # result = model.transcribe(audio_path, at_time_res=audio_tagging_time_resolution)
+    result = model.transcribe(audio_path, at_time_res=audio_tagging_time_resolution)
     # # ASR Results
     # print(result["text"])
     # # Audio Tagging Results
@@ -32,7 +32,7 @@ def predict(audio_path, time_resolution):
     #     print(segment)
     #     at_output = at_output + str(segment['time']['start']) + 's-' + str(segment['time']['end']) + 's: ' + ','.join([x[0] for x in segment['audio tags']]) + '\n'
     #     print(at_output)
-    asr_output, at_output = str(audio_tagging_time_resolution), 'k'
+    asr_output, at_output = str(result["text"]), 'k'
     return asr_output, at_output
 
 iface = gr.Interface(fn=predict,